eCBRa Logo

eCBRa Wordmark

easy Case-Based Reasoning agent

We call it e-Zebra!

Release Date: 2026 April 9
Latest version: 1.0
Editors:
Andreas Korger, University of Würzburg, DE
Contact:
(Collaborations and contributions welcome:)
info[at]piri-safety.com

Abstract

The eCBRo Ontology is designed to represent semantic concepts and relationships relevant to the Case-Based Reasoning (CBR)[1] paradigm, utilizing the OWL2 Web Ontology Language[2]. Its primary goal is to offer a framework of classes, properties, and constraints that allow for the organization of information into specific cases in a manner that is both lightweight and adaptable. This ontology can be tailored to meet the individual needs of various CBR applications, with its elements demonstrated through practical examples in the fire safety domain.

Overview

Organizing knowledge into cases proves valuable across a wide range of domains. In many situations, the goal is not to develop a complete Case-Based Reasoning system from the outset. Instead, case bases and their internal structure tend to evolve incrementally, often integrating input from diverse and distributed sources before forming a mature CBR system. To support these early development phases—as well as other multimodal, distributed, and dynamic CBR scenarios—a flexible semantic framework is needed to represent layered semantic case features and related CBR knowledge.

Therefore, this website presents eCBRo, a lightweight ontology crafted with a case-centric semantic perspective. The ontology is described in detail and incrementally exemplified through use cases within the domain of fire safety. It illustrates how LLM-assisted case acquisition from a nuclear fire safety document and distributed case design within paradigms such as the Model Context Protocol (MCP)[3] can be effectively implemented.

Classes: 16
ecbro:CBRConcept, ecbro:Case, ecbro:Client, ecbro:CaseBase, ecbro:Input, ecbro:Output, ecbro:AttributeValue, ecbro:Attribute, ecbro:Value, ecbro:Description, ecbro:Problem, ecbro:Solution, ecbro:Similarity
Properties: 20
ecbro:partOf, ecbro:input, ecbro:output, ecbro:hasInput, ecbro:hasOutput, ecbro:hasAttributeValue, ecbro:hasAttribute, ecbro:hasValue, ecbro:hasDescription, ecbro:hasProblem, ecbro:hasSolution, ecbro:hasSimilarity, ecbro:retrieve, ecbro:reuse, ecbro:revise, ecbro:retain

Ontology Graph

eCBRo Ontology Overview

The full ontology graph shows relationships between biomedical research concepts. Use ontology visualization tools (like WebVOWL or OWLViz) to explore the complete structure.

References

  1. Kolodner, J. L. (1993). Case-based reasoning. San Mateo, CA: Morgan Kaufmann.
  2. Motik, B., Patel-Schneider, P. F., & Parsia, B. (2012). OWL 2 Web Ontology Language Document Overview (Second Edition). W3C Recommendation. Retrieved from https://www.w3.org/TR/owl2-overview/
  3. Anthropic (2024–2025). Introducing the Model Context Protocol — a W3C-style whitepaper introducing MCP as an open standard to connect AI models with external tools and data sources. Released November 25, 2024, MCP enables secure, bidirectional integration across tools and datasets.